• Own backend services end-to-end: architecture, implementation, infrastructure, deployment, production, scaling • Design and operate high-throughput, low-latency Java services (JDK 17+) on AWS, K8s, Terraform • Build resilient distributed components and tune memory, concurrency, and GC • Own CI/CD, observability, and on-call for systems shipped

• tworzenie lub rozbudowywanie środowisk, na których działa przygotowywane przez zespół oprogramowanie, • dbanie o to, aby stacje robocze programistów i testerów były przygotowane do pracy w projekcie w sposób w pełni zautomatyzowany, • budowanie i utrzymywanie narzędzi służących do automatyzacji procesu wytwarzania oprogramowania we wszystkich jego fazach, • dbanie o zachowanie odpowiedniego balansu między wysokim poziomem bezpieczeństwa a wygodą i elastycznością pracy zespołu, • wdrażanie nowych członków zespołu w obszarze Twojej odpowiedzialności i nadawanie uprawnień, • przygotowywanie dokumentacji (lecz jeśli osiągniesz odpowiedni wysoki poziom automatyzacją, Twoją dokumentacją będzie również Twój kod), • przygotowywanie rożnych komponentów infrastrukturalny takich jak Reverse Proxy, usługi monitorujące lub agregatory logów,

• Ensure the performance and reliability of mission-critical trading infrastructure by proactively identifying and resolving bottlenecks at all layers: compute, network, storage, and application. • Support, operate, and continuously improve highly available, low-latency systems under global trading load, with a strong focus on automation and enabling self-service for internal teams. • Participate in a day-time rotational on-call schedule, handling real-time operational incidents, root cause analysis, and long-term preventive improvements. • Use metrics and observability tools (Prometheus, Grafana, etc.) to detect anomalies, monitor performance trends, and support incident response. • Build, manage, and scale infrastructure-as-code using Terraform and configuration management tools like Ansible. • Collaborate closely with trading, engineering, and security teams to align infrastructure improvements with application demands. • Implement robust security practices, including IAM, threat detection, and secure CI/CD pipelines, to support high-trust production environments. • Apply low-level optimization strategies to improve throughput, reduce latency, and increase system efficiency across diverse environments. • Work closely with developers, traders and other staff to accomplish our firm’s goals.

Role Description Own ARIP's operational substrate — infrastructure-as-code (on Data Engineering & Advanced Analytic (DEAA's) Terraform standard), CI/CD pipelines with eval-gate enforcement, per-agent observability, per-agent cost meter, FinOps, and incident response. Inherit production environment from Databricks contractor in Q1 2027 and harden it for Wave 3 scale across 15 agents and 5 suites. Remote candidates outside of Thailand are welcome to apply. - Adopt DEAA's Terraform standard for all ARIP infrastructure; author ARIP-specific modules (agent runtime, vector DB, KG database); weekly drift detection — zero unmanaged production resources - Build ARIP CI/CD pipelines on DEAA's spine with eval-gate enforcement — no agent reaches production without eval-pass; ≤1hr deployment lead time, ≤15min rollback time - Implement per-agent cost meter end-to-end (LLM tokens, vector DB queries, model inference) and surface to DEAA's GenAI Cost Dashboard (DTB-51) - Stand up ARIP on-call rotation; author runbooks for every production agent and service; lead incident response; MTTR < 60min for P0/P1 - Implement ARIP cost tagging policy (team / domain / environment / agent / suite / persona) aligned with DEAA's standard; report monthly to ARIP Cost Review - Execute Databricks contractor hand-over in Q1 2027: inherit IaC, runbooks, observability; refactor to Lotus's standards. Qualifications - 5+ years SRE / DevOps with production ownership of AI / data-intensive or agent-based platforms - Terraform at enterprise scale: modules, state management, drift detection, environment promotion — expert; Terraform Associate / Professional preferred - CI/CD for ML/AI services: GitLab CI/CD or comparable with eval-gate integration; cloud (Azure preferred); AZ-500 helpful - OpenTelemetry + Langfuse (or equivalent) for LLM observability in production; FinOps: tagging policies, per-invocation cost attribution for LLM systems - Incident response: on-call, post-mortems, runbook authorship at senior level; rollback orchestration with quarterly game days - Calibre: Senior DevOps / SRE from Agoda, Grab, Shopee, LINE MAN Wongnai, SCBX, KBank, or AI-native infra teams.